---
title: 'Inference Engineering, Co-op at Inferact'
canonical: 'https://feeny.ai/job/inference-engineering-co-op-inferact-san-francisco-zxysczbanr0y'
type: 'job'
last_seen: '2026-09-15'
---

# Inference Engineering, Co-op at Inferact

- **Company:** Inferact
- **Location:** San Francisco, CA
- **Employment:** internship
- **Work type:** onsite
- **Posted:** 2026-09-10
- **Last confirmed live:** 2026-09-15
- **Apply:** https://jobs.ashbyhq.com/inferact/2b6032f9-12a5-4083-b5e6-4bec5376cbaa

## Job description

## Overview

Inferact's mission is to grow vLLM as the world's AI inference engine and accelerate AI progress by making inference cheaper and faster. Founded by the creators and core maintainers of vLLM, we sit at the intersection of models and hardware, a position that took years to build.

## About the Role

We're looking for exceptional University of Waterloo co-op students who want to work on the systems that determine how fast, efficiently, and reliably frontier AI models run on frontier workloads at scale. This is not a sandboxed internship project. We will match your strengths and interests to a real engineering problem across the vLLM stack, from model execution and low-level accelerator code to distributed serving and the cloud platform that makes it all usable. You'll work alongside the creators and core maintainers of vLLM on work intended to ship into open source, production systems, or the tooling that supports both. You will have a primary technical track, meaningful ownership, and mentorship from a small, senior team, with opportunities to collaborate across models, compilers, accelerators, networking, and distributed systems. The goal is to let exceptional students learn at the frontier while making contributions used by developers and AI teams around the world.

Potential Focus Areas Your co-op will have a primary home in one of the following tracks, with opportunities to contribute across others:

- Inference Runtime: Bring new model architectures and inference techniques to life in vLLM. Implement ideas from research papers; support mixture-of-experts, multimodal, diffusion, and agentic workloads; and improve scheduling, continuous batching, KV-cache memory management, prefix caching, and hybrid model serving.
- Performance & Scale: Build the distributed serving data plane that lets vLLM run across many GPUs and nodes. Work on tensor, expert, or context parallelism; prefill/decode separation and KV-cache transport; fault tolerance and multi-tenancy; and high-performance communication using NCCL, DeepEP, NVSHMEM, RDMA, or InfiniBand.
- Kernel Engineering: Raise the hardware performance ceiling by writing and optimizing attention, GEMM, sampling, KV-cache, fused, and quantization kernels. Use CUDA, Triton, TileLang, CUTLASS/CUTE, or related tools; reason about memory hierarchy, occupancy, and tensor cores; and prove speedups through profiling, correctness tests, and reproducible benchmarks.
- AMD GPU Performance: Help make vLLM first-class on AMD accelerators. Work across ROCm, HIP, Triton, CK, AITER, kernels, runtime paths, quantization, compiler integration, and performance-regression infrastructure while learning how AMD-specific execution, memory, and toolchain constraints shape inference.
- TPU Performance: Help make vLLM fast and correct on Google TPUs. Build backend, runtime, and compiler integrations with JAX, XLA, Pallas, MLIR, and related tooling; inspect compiler artifacts; work on lowering, fusion, and code generation; and benchmark production-relevant serving across correctness, latency, and throughput.
- Cloud Orchestration: Build the operational platform that makes large-scale inference deployable and reliable. Work on Kubernetes and custom operators, topology-aware GPU scheduling, zero-downtime vLLM rollouts, token-aware routing, observability, infrastructure-as-code, automated recovery, and bring-your-own-cloud or multi-cloud fleet management.

You are not expected to arrive with experience in every track. We care most about unusual depth or learning velocity in one area, strong fundamentals, and evidence that you can turn a difficult problem into working, measurable software.

## Skills and Qualifications

Minimum qualifications:

- Currently pursuing a bachelor's, master's, or PhD degree in computer science, engineering, mathematics, or a related technical field, and eligible for a University of Waterloo co-op work term.
- Strong programming ability in Python, C++, Rust, Go, or another systems-oriented language.
- Strong computer science fundamentals and the ability to learn from research papers, technical documentation, and complex systems code.
- Evidence that you have built and debugged nontrivial software through coursework, research, a prior internship, open-source work, or an ambitious side project.
- A builder mindset: you define what success means, measure results, validate correctness, communicate clearly, and keep iterating until the system works.

Preferred qualifications:

- Depth in at least one relevant area such as ML or inference systems, distributed systems, GPU or accelerator programming, compilers, high-performance computing, operating systems, networking, Kubernetes, or cloud infrastructure.
- Hands-on experience with one or more relevant technologies such as PyTorch, vLLM, SGLang, TensorRT-LLM, CUDA, Triton, TileLang, ROCm/HIP, JAX/XLA, Pallas, Kubernetes, Helm, Terraform, Ray, or SLURM.
- Experience profiling or benchmarking software, validating numerical or systems correctness, or building tests that protect against performance regressions.
- Experience with systems beyond a single local process or device, including multi-GPU, multi-node, research-cluster, high-throughput, or production-like workloads.

Bonus points if you have:

- Contributed to open-source ML, systems, compiler, or infrastructure projects, especially vLLM or adjacent projects.
- Built a research system, benchmark suite, compiler or kernel project, distributed service, or infrastructure tool that demonstrates unusual technical depth and initiative.
- Worked across more than one layer of the stack and enjoy moving between algorithms, runtimes, systems, and hardware rather than staying inside a single abstraction.
- Created a technical artifact such as a paper, design document, blog post, demo, or talk that clearly explains what you built and what you learned.

Logistics

- Location: San Francisco, California. This co-op is in-office only at Inferact's San Francisco office and is intended for the University of Waterloo co-op program.
- Work term: Co-op / internship. Exact dates will align with the applicable Waterloo work term.
- Compensation: Competitive compensation based on the applicable co-op market and candidate background, plus a housing stipend for the duration of the co-op term.

## About Inferact

## Company Overview
- **One-liner**: Inferact is a startup founded by the creators of vLLM, the leading open-source LLM inference engine, dedicated to making AI inference cheaper and faster at global scale.
- **Entity Type**: Private (Seed stage; raised $150M in seed funding)
- **Headquarters**: San Francisco, California, United States (with a second office in Singapore)
- **Founded**: 2025
- **Founders**: Simon Mo (CEO), Woosuk Kwon, Kaichao You (Chief Scientist), Roger Wang, Joseph Gonzalez, Ion Stoica

## Core Business
- **Primary industry**: AI infrastructure / open-source inference engine for large language models
- **Target customers**: AI labs, hyperscalers, startups, and enterprises deploying large-scale AI models (B2B, primarily technical teams)
- **Mission**: Grow vLLM as the world’s AI inference engine and accelerate AI progress by making inference cheaper and faster.

## Products & Services
- **vLLM (Open-Source Inference Engine)**: The core product – an open-source LLM inference engine that supports 500+ model architectures and runs on 200+ accelerator types. Inferact stewards and supercharges vLLM, with all optimizations flowing back to the community.
- **Managed Inference Infrastructure (in development)**: Inferact is building infrastructure to absorb the complexity of deploying frontier models at scale, aiming to make it as simple as spinning up a serverless database.

## Market Standing
- **Valuation/Market Cap**: Not disclosed (private company)
- **Key Metric**: Total funding of $150M (seed round, announced 2026)
- **Notable Investors/Partners**: Lightspeed Venture Partners (lead), Redpoint Ventures, Andreessen Horowitz, Altimeter Capital, Sequoia Capital, The House Fund, GC&H Investments, and others. Partnerships include NVIDIA, Red Hat, DigitalOcean, and Cohere.
- **Growth Signals**: 
  - $150M seed round – one of the largest seed rounds in AI infrastructure.
  - 22 employees with +27.3% monthly headcount growth.
  - vLLM ecosystem: 2,000+ contributors, 500+ model architectures, 200+ accelerator types.
  - Day-zero support for new model architectures (e.g., Cohere’s Command A+) and hardware integrations.
  - Active hiring with 5 open positions across inference, performance, kernel engineering, and cloud orchestration.

## Competitive Advantages
- **Deep ecosystem moat**: vLLM is the de facto standard open-source inference engine, with a massive community and integrations across models and hardware that took years to build.
- **Founding team credibility**: Creators and core maintainers of vLLM, with experience deploying at frontier scale (research and production).
- **Hardware-software co-optimization**: Positioned at the intersection of model innovation and hardware diversity, enabling day-zero compatibility and performance optimizations.
- **Open-source commitment**: All improvements flow back to vLLM, ensuring community trust and rapid adoption.

## Strategic Focus
- **Current priorities**: Push vLLM performance further, deepen support for emerging model architectures (MoE, multimodal, agentic), expand hardware coverage (200+ accelerators), and build managed infrastructure to simplify deployment.
- **Growth direction**: Close the capability gap between models and serving systems; absorb complexity so teams can focus on innovation rather than infrastructure.

## Why Work Here
- **Culture**: High-caliber engineering team with roots in vLLM, PyTorch, and top AI labs. Emphasis on open-source contribution and cutting-edge inference research.
- **Work policy**: Hybrid with a San Francisco HQ; at least one open role (Member of Technical Staff, Exceptional Generalist) is listed as Remote.
- **Notable perks**: Opportunity to work at the frontier of AI inference, directly impact the open-source ecosystem, and collaborate with partners like NVIDIA, Red Hat, and major AI labs.
- **Engineering culture**: Strong focus on systems engineering, kernel optimization, and cloud orchestration – ideal for engineers passionate about performance and infrastructure.

## Sources
1. [inferact.ai](https://inferact.ai/)
2. [LinkedIn](https://www.linkedin.com/company/inferact)
3. [CB Insights](https://www.cbinsights.com/company/inferact)
4. [Sequoia Capital](https://sequoiacap.com/companies/inferact/)
5. [Ashby Jobs](https://jobs.ashbyhq.com/inferact)

## Other roles at Inferact

- [Founding Product Designer](https://feeny.ai/job/founding-product-designer-inferact-san-francisco-8fhyc666jrb6) — San Francisco, CA
- [IT Support & Operations Engineer](https://feeny.ai/job/it-support-operations-engineer-inferact-san-francisco-jfknsmecptdj) — San Francisco, CA
- [Head of Legal](https://feeny.ai/job/head-of-legal-inferact-san-francisco-8za70prrkyas) — San Francisco, CA
- [HR / People Lead](https://feeny.ai/job/hr-people-lead-inferact-san-francisco-qc5yjw670w1d) — San Francisco, CA
- [Member of Technical Staff, Inference](https://feeny.ai/job/member-of-technical-staff-inference-inferact-remote-ezb6x9bq2fty)
- [Member of Technical Staff, Cloud Orchestration (Remote)](https://feeny.ai/job/member-of-technical-staff-cloud-orchestration-remote-inferact-remote-pzza0bak1bw7)
- [Member of Technical Staff, Cluster Administration](https://feeny.ai/job/member-of-technical-staff-cluster-administration-inferact-san-francisco-hzy2pmhsv4ca) — San Francisco, CA
- [Member of Technical Staff, Site Reliability Engineer](https://feeny.ai/job/member-of-technical-staff-site-reliability-engineer-inferact-san-francisco-4hdd72zebn0b) — San Francisco, CA
- [Head of Engineering](https://feeny.ai/job/head-of-engineering-inferact-san-francisco-rhcv5bpns37j) — San Francisco, CA
- [Product Marketing Manager](https://feeny.ai/job/product-marketing-manager-inferact-san-francisco-ap07axndjdjb) — San Francisco, CA